Spaces:
Running
Running
File size: 3,094 Bytes
372a807 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 |
import streamlit as st
from typing import List, IO
# Import utilities you finalised
from utils import (
get_pdf_text,
get_docx_text,
get_text_chunks,
get_vector_store,
user_input,
)
# ---------------------------------------------------------------------------#
# Main Streamlit application
# ---------------------------------------------------------------------------#
def main() -> None:
# ----- Page configuration ------------------------------------------------
st.set_page_config(
page_title="Docosphere",
page_icon="📄",
layout="wide"
)
st.title("📄 Docosphere")
st.markdown("*Where Documents Come Alive …*")
# Two-column layout: Q&A on left, file upload on right
col_left, col_right = st.columns([2, 1])
# --------------------- Right column – document upload -------------------
with col_right:
st.markdown("### 📁 Document Upload")
uploaded_files: List[IO[bytes]] = st.file_uploader(
"Upload PDF or Word files",
accept_multiple_files=True,
type=["pdf", "docx"],
help="You can select multiple files at once."
)
if st.button("🚀 Process Documents"):
if not uploaded_files:
st.warning("📋 Please upload at least one file first.")
return
with st.spinner("🔄 Extracting text & creating vector index…"):
combined_text = ""
pdfs = [f for f in uploaded_files if f.name.lower().endswith(".pdf")]
docs = [f for f in uploaded_files if f.name.lower().endswith(".docx")]
if pdfs:
combined_text += get_pdf_text(pdfs)
if docs:
combined_text += get_docx_text(docs)
if combined_text.strip():
chunks = get_text_chunks(combined_text)
get_vector_store(chunks)
st.success("✅ Documents processed! Ask away in the left panel.")
else:
st.warning("⚠️ No readable text found in the uploaded files.")
with st.expander("ℹ️ How to use"):
st.markdown(
"""
1. Upload one or more **PDF** or **Word** documents.\n
2. Click **Process Documents** to build the knowledge index.\n
3. Ask natural-language questions in the input box (left column).\n
4. The assistant will either answer from its own model knowledge or
retrieve context from your documents when needed.
"""
)
# ---------------------- Left column – chat interface --------------------
with col_left:
st.markdown("### 💬 Ask Your Question")
question: str = st.text_input(
"",
placeholder="Type a question about your documents or general topics…"
)
if question:
user_input(question)
# Entry-point guard
if __name__ == "__main__":
main()
|